Improvements of Hidden Chunk Models


The statistical properties of segments [8] using a specific acoustic model called the hidden chunk model (HCM) is investigated. We call the sequence of feature vectors assigned to a segment a chunk of length l. The HCM still assumes that the feature vectors are statistically independent. In contrast to hidden Markov model (HMM) we introduce emission probabilities which depend on l. Segment error rates (SERs) are calculated on a database with over 33 million chunks aligned to 607 segments. The HCM achieves more than 10%absolute improvement in SER compared to the HMM. Based on the estimated Shannon’s entropy, the proposed HCM model paves the way to create acoustic models which are heading towards the lowest possible SER.

Year: 2010
In session: Speech Recognition
Pages: 220 to 227